基于半监督聚类的煤泥浮选泡沫图像分类方法

详细信息    查看全文 | 推荐本文 |

英文篇名：Coal slime flotation foam image classification method based on semi-supervised clustering 作者：曹文艳 ; 王然风 ; 樊民强 ; 付翔 ; 王宇龙 英文作者：CAO Wenyan;WANG Ranfeng;FAN Minqiang;FU Xiang;WANG Yulong;College of Mining Engineering,Taiyuan University of Technology; 关键词：选煤厂 ; 煤泥浮选 ; 浮选泡沫 ; 加药量 ; 图像特征提取 ; 半监督聚类 ; 高斯混合模型 英文关键词：coal preparation plant;;coal slime flotation;;flotation foam;;reagent-addition amount;;image feature extraction;;semi-supervised clustering;;Gaussian mixture model 中文刊名：MKZD 英文刊名：Industry and Mine Automation 机构：太原理工大学矿业工程学院; 出版日期：2019-07-08 14:10 出版单位：工矿自动化 年：2019 期：v.45;No.280 基金：山西省科技计划研究项目(201801D221358) 语种：中文; 页：MKZD201907008 页数：6 CN：07 ISSN：32-1627/TP 分类号：41-45+68

摘要

针对选煤厂煤泥浮选过程加药量依靠人工干预存在主观性、滞后性和粗放性的问题,提出了一种基于半监督聚类的煤泥浮选泡沫图像分类方法。首先,采集已知加药比例与未知加药比例下的煤泥浮选泡沫图像样本,并对泡沫图像进行预处理,提取泡沫的气泡个数、气泡面积、气泡周长等形态特征;然后,对已知加药比例下泡沫图像形态特征样本进行标志,对未知加药比例下泡沫图像形态特征样本不做标志,并将已标志泡沫图像形态特征样本与未标志泡沫图像形态特征样本进行混合;最后,利用基于高斯混合模型的半监督聚类方法对混合样本进行聚类后得到各类簇,将各类簇内已标志泡沫图像形态特征样本的信息映射到未标志泡沫图像形态特征样本。应用结果表明,该方法可为煤泥浮选生产过程加药量调整提供指导,降低了药剂消耗量,提高了选煤厂浮选自动化水平和经济效益。
        In order to solve problems of subjectivity,hysteresis and extensiveness existed in reagent amount addition of coal slime flotation in coal preparation plant depended on manual intervention,a coal slime flotation foam image classification method based on semi-supervised clustering was proposed.Firstly,coal slime flotation foam images under known reagent-addition ratio and unknown reagent-addition ratio are collected,and the foam images are preprocessed to extract morphological characteristics such as bubble number,bubble area and bubble perimeter.Then,foam image morphological characteristic samples under known reagent-addition ratio are marked,while foam image morphological characteristic samples under unknown reagent-addition ratio are not marked,and the marked foam image morphological characteristic samples and the unmarked foam image morphological characteristic samples are mixed.Finally,semi-supervised clustering method based on Gaussian mixture model is used to cluster the mixed samples,so as to get various clusters,and information of the marked foam image morphological characteristic samples is mapped to the unmarked foam image morphological characteristic samples in various clusters.The application results show that the method can provide guidance for adjustment of reagent-addition amount in coal slime flotation production process,reduce consumption of reagent,and improve flotation automation level and economic benefit of coal preparation plant.

引文

[1]吴翠平,杨小平,许德平,等.在线煤浆灰分测量的煤泥浮选优化控制系统研究[J].高技术通讯,2003,13(8):85-90.WU Cuiping,YANG Xiaoping,XU Deping,et al.Study of a coal slurry floatation optimizing control system based on ash on-line measurement[J].Chinese High Technology Letters,2003,13(8):85-90.
    [2]史纪录,朱正军.浮选自动加药装置的研制与应用[J].选煤技术,2014(3):68-71.SHI Jilu,ZHU Zhengjun.Study and application of flotation automatic dosing device[J].Coal Preparation Technology,2014(3):68-71.
    [3]曾荣,沃国经.图像处理技术在镍选矿厂中的应用[J].矿冶,2002,11(1):37-41.ZENG Rong,WO Guojing.Application of the image processing technology in nickel concentrator[J].Mining &Metallurgy,2002,11(1):37-41.
    [4]周开军,阳春华,牟学民,等.一种基于图像特征提取的浮选回收率预测算法[J].高技术通讯,2009,19(9):957-963.ZHOU Kaijun,YANG Chunhua,MU Xuemin,et al.A flotation recovery prediction algorithm based on image feature extraction[J].Chinese High Technology Letters,2009,19(9):957-963.
    [5]李建奇,阳春华,曹斌芳,等.面向参数测量的改进分水岭浮选泡沫图像分割方法[J].仪器仪表学报,2013,34(6):34-41.LI Jianqi,YANG Chunhua,CAO Binfang,et al.Improved watershed segmentation method for flotation froth image based on parameter measurement[J].Chinese Journal of Scientific Instrument,2013,34(6):34-41.
    [6]牟学民,刘金平,桂卫华,等.基于SIFT特征配准的浮选泡沫移动速度提取与分析[J].信息与控制,2011,40(4):525-531.MU Xuemin,LIU Jinping,GUI Weihua,et al.Flotation froth motion velocity extraction and analysis based on SIFT features registration[J].Information and Control,2011,40(4):525-531.
    [7]桂卫华,阳春华,谢永芳,等.矿物浮选泡沫图像处理与过程监测技术[M].长沙:中南大学出版社,2013.
    [8]路迈西,王勇,王凡,等.利用阈值分割技术提取煤泥浮选泡沫图像的物理特征[J].煤炭科学技术,2002,30(8):34-37.LU Maixi,WANG Yong,WANG Fan,et al.Threshold segmentation technology applied to get physical features of foam image from slime floatation[J].Coal Science and Technology,2002,30(8):34-37.
    [9]刘文礼,路迈西,王凡,等.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别[J].化工学报,2003,54(6):830-835.LIU Wenli,LU Maixi,WANG Fan,et al.Extraction of textural feature and recognition of coal flotation froth[J].Journal of Chemical Industry and Engineering,2003,54(6):830-835.
    [10]平翠霞.铝土矿浮选泡沫尺寸分布特征与浮选药剂添加量关系模型[D].长沙:中南大学,2012.
    [11]董志勇,王然风,樊民强,等.基于PSO-LSSVM的煤泥浮选药剂自动添加系统研究[J].煤炭工程,2017,49(2):117-120.DONG Zhiyong,WANG Ranfeng,FAN Minqiang,et al.Research on automatic dosing system for coal slime flotation based on PSO-LSSVM[J].Coal Engineering,2017,49(2):117-120.
    [12]唐朝晖,王伟,刘金平,等.基于泡沫尺寸PDF模型的铜粗选过程加药量预测控制[J].中南大学学报(自然科学版),2015,46(3):856-863.TANG Zhaohui,WANG Wei,LIU Jinping,et al.Predictive control of reagent-addition amount based on PDF model of bubble size in copper roughing flotation process[J].Journal of Central South University(Science and Technology),2015,46(3):856-863.
    [13]肖金林,桂卫华.浮选泡沫图像监控系统在冬瓜山铜矿的应用[J].科协论坛(下半月),2012(6):70-71.
    [14]刘恒.铜浮选泡沫图像监控系统的构件化软件设计[D].长沙:中南大学,2013.
    [15]欧阳长恒.基于MATLAB的煤泥浮选泡沫图像分析方法研究[D].徐州:中国矿业大学,2017.
    [16]林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007,32(3):304-308.LIN Xiaozhu,GU Yingying,ZHAO Guoqing.Feature extraction based on image segmentation of coal flotation froth[J].Journal of China Coal Society,2007,32(3):304-308.
    [17]林小竹,王彦敏,杜天苍,等.基于分水岭变换的目标图像的分割与计数方法[J].计算机工程,2006,32(15):181-183.LIN Xiaozhu,WANG Yanmin,DU Tiancang,et al.A segment and count method based on watershed transformation[J].Computer Engineering,2006,32(15):181-183.
    [18]罗胜,郑蓓蓉,叶忻泉.基于EM和GMM相结合的自适应灰度图像分割算法[J].光子学报,2009,38(6):1581-1585.LUO Sheng,ZHENG Beirong,YE Xinquan.Image segment based on the self-adaptive threshold EM and GMM algorithm[J].Acta Photonica Sinica,2009,38(6):1581-1585.
    [19]王民,张鑫,贠卫国,等.基于核模糊C-均值和EM混合聚类算法的遥感图像分割[J].液晶与显示,2017,32(12):999-1005.WANG Min,ZHANG Xin,YUN Weiguo,et al.Remote sensing image segmentation based on KFCM and EM hybrid clustering algorithm[J].Chinese Journal of Liquid Crystals and Displays,2017,32(12):999-1005.